Editing voice input

• US 8,244,544 B1
• Filed: 09/29/2011
• Issued: 08/14/2012
• Est. Priority Date: 08/06/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: LeBeau, Michael J., Jitkoff, John Nicholas, Byrne, William J.
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US13/248,849
• Time in Patent Office: 320 Days
• Field of Search: 704 1- 10, 704/251, 704/252, 704/253, 704/254, 704/257, 704/270, 704/235, 704/231, 704/275, 704/270.1
• US Class Current: 704/275
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/0638 Interactive procedures
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A computer-implemented method of generating a voice command to perform an action includes receiving a voice request to perform the action, wherein the voice request comprises first audio information for one or more first data fields associated with the action; generating a GUI that when rendered on a display device comprises a prompt message prompting a user to speak second audio information for one or more second data fields associated with the action; and inserting into the one or more second data fields data indicative of one or more of (i) the first audio information, and (ii) the second audio information.

Claims

1. A method comprising:

receiving, by a processing device, a voice request to perform an action, wherein the voice request comprises first audio information associated with the action;

generating, by the processing device, information for a GUI that when rendered on a display device renders a prompt message prompting a user to speak second audio information associated with the action;

determining, based on the voice request, a syntax format to be used in performing the action, wherein the syntax format comprises one or more data fields;

generating syntax information, with the syntax information at least partly based on one or more of (i) the first audio information, and (ii) the second audio information;

inserting, by the processing device into the one or more data fields, the syntax information;

determining, based on inserting, one or more incomplete data fields; and

generating, based on the one or more incomplete data fields, one or more training actions to train the user to speak a complete syntax associated with the action.

2. The method of claim 1, further comprising:

determining that the first audio information comprises a partial set of information for the one or more data fields.

3. The method of claim 1, further comprising:

receiving, in response to the one or more training actions, third audio information; and

determining that the first audio information, the second audio information and the third audio information comprise a complete set of information for the one or more data fields.

4. The method of claim 1, further comprising:

retrieving, from a data repository, one or more syntax rules;

applying the one or more syntax rules to the syntax information; and

generating, based on applying, a mapping between the one or more data fields and the syntax information.

5. The method of claim 1, wherein the GUI comprises a first GUI, and wherein at least one of the one or more training actions comprise information for a second GUI that when rendered on the display device renders a highlighted visual representation of at least one of the one or more incomplete data fields.

6. The method of claim 1, further comprising:

retrieving a template for performance of the action, wherein the template comprises an ordering of the one or more data fields.

7. One or more non-transitory machine-readable media configured to store instructions that are executable by one or more processing devices to perform operations comprising:

receiving a voice request to perform an action, wherein the voice request comprises first audio information associated with the action;

generating information for a GUI that when rendered on a display device renders a prompt message prompting a user to speak second audio information associated with the action;

determining, based on the voice request, a syntax format to be used in performing the action, wherein the syntax format comprises one or more data fields;

generating syntax information, with the syntax information at least partly based on one or more of (i) the first audio information, and (ii) the second audio information;

inserting, into the one or more data fields, the syntax information;

determining, based on inserting, one or more incomplete data fields; and

generating, based on the one or more incomplete data fields, one or more training actions to train the user to speak a complete syntax associated with the action.

8. The one or more non-transitory machine-readable media of claim 7, wherein the operations further comprise:

determining that the first audio information comprises a partial set of information for the one or more data fields.

9. The one or more non-transitory machine-readable media of claim 7, wherein the operations further comprise:

receiving, in response to the one or more training actions, third audio information; and

determining that the first audio information, the second audio information and the third audio information comprise a complete set of information for the one or more data fields.

10. The one or more non-transitory machine-readable media of claim 7, wherein the operations further comprise:

retrieving, from a data repository, one or more syntax rules;

applying the one or more syntax rules to the syntax information; and

generating, based on applying, a mapping between the one or more data fields and the syntax information.

11. The one or more non-transitory machine-readable media of claim 7, wherein the GUI comprises a first GUI, and wherein at least one of the one or more training actions comprise information for a second GUI that when rendered on the display device renders a highlighted visual representation of at least one of the one or more incomplete data fields.

12. The one or more non-transitory machine-readable media of claim 7, wherein the operations further comprise:

retrieving a template for performance of the action, wherein the template comprises an ordering of the one or more data fields.

13. An electronic system comprising:

one or more processing devices; and

one or more machine-readable media configured to store instructions that are executable by the one or more processing devices to perform operations comprising;

receiving a voice request to perform an action, wherein the voice request comprises first audio information associated with the action;

generating information for a GUI that when rendered on a display device renders a prompt message prompting a user to speak second audio information associated with the action; and

determining, based on the voice request, a syntax format to be used in performing the action, wherein the syntax format comprises one or more data fields;

generating syntax information, with the syntax information at least partly based on one or more of (i) the first audio information, and (ii) the second audio information;

inserting, into the one or more second data fields, the syntax information;

determining, based on inserting, one or more incomplete data fields; and

generating, based on the one or more incomplete data fields, one or more training actions to train the user to speak a complete syntax associated with the action.

14. The electronic system of claim 13, wherein the operations further comprise:

determining that the first audio information comprises a partial set of information for the one or more data fields.

15. The electronic system of claim 13, wherein the devices to operations further comprise:

receiving, in response to the one or more training actions, third audio information; and

determining that the first audio information, the second audio information and the third audio information comprise a complete set of information for the one or more data fields.

16. The electronic system of claim 13, wherein the operations further comprise:

retrieving, from a data repository, one or more syntax rules;

applying the one or more syntax rules to the syntax information; and

generating, based on applying, a mapping between the one or more data fields and the syntax information.

17. The electronic system of claim 13, wherein the GUI comprises a first GUI, and wherein at least one of the one or more training actions comprise information for a second GUI that when rendered on the display device renders a highlighted visual representation of at least one of the one or more incomplete data fields.

18. The electronic system of claim 13, wherein the operations further comprise:

retrieving a template for performance of the action, wherein the template comprises an ordering of the one or more data fields.

19. An electronic system comprising:

a voice editor manager configured to;

receive and a voice request to perform an action, wherein the voice request comprises first audio information associated with the action;

means for generating information for a GUI that when rendered on a display device renders a prompt message prompting a user to speak second audio information associated with the action;

means for determining, based on the voice request, a syntax format to be used in performing the action, wherein the syntax format comprises one or more data fields;

means for generating syntax information, with the syntax information at least partly based on one or more of (i) the first audio information, and (ii) the second audio information;

means for inserting, into the one or more data fields, the syntax information;

means for determining, based on inserting, one or more incomplete data fields; and

means for generating, based on the one or more incomplete data fields, one or more training actions to train the user to speak a complete syntax associated with the action.

20. The electronic system of claim 19, further comprising:

means for determining that the first audio information comprises a partial set of information for the one or more data fields.

21. The electronic system of claim 19, further comprising:

means for receiving, in response to the one or more training actions, third audio information; and

means for determining that the first audio information, the second audio information and the third audio information comprise a complete set of information for the one or more data fields.

22. The electronic system of claim 19, further comprising:

means for retrieving, from a data repository, one or more syntax rules;

means for applying the one or more syntax rules to the syntax information; and

means for generating, based on applying, a mapping between the one or more data fields and the syntax information.

23. The electronic system of claim 19, wherein the GUI comprises a first GUI, and wherein at least one of the one or more training actions comprise information for second GUI that when rendered on the display device renders a highlighted visual representation of at least one of the one or more incomplete data fields.

24. The electronic system of claim 19, further comprising:

means for retrieving a template for performance of the action, wherein the template comprises an ordering of the one or more data fields.